Amazon Technologies, Inc.

Kyle Andrew Farrell

Michael C Moore

Nirav Praful Desai

Stanislava R Vlasseva

Stanislav Fritz

Nirav J Desai

Gurbinder Gill

Suzuko Chida

Ravikumar Makam

Kyung Deuk Park

An environment and techniques for intelligently selecting which tests of multiple different tests to run on a particular section or sections of code, such as one or more lines of code that a developer has altered, are described herein. In this manner, the techniques may allow developers to receive feedback on their software more quickly by running a subset of tests, rather than each test in a predefined set of tests.

Selecting appropriate subsets of software tests

An architecture and techniques for implementing a unified and extensible meta-testing framework within a distributed environment. This framework allows entities within the distributed environment to run tests written in different testing frameworks in a unified way. In addition, this disclosure describes techniques for allowing an entity within the distributed environment to test itself, both from its own perspective as well as from the perspective of other entities within the distributed environment.

Self-service testing

A stubbing service records requests and corresponding replies for purpose of playing back the recorded replies in response to re-receiving the corresponding requests. In a record mode, the stubbing service may receive a request from a first service intended for a second service. The stubbing service may send the request onto the second service and may, in response, receive a reply to the request from the second service. The stubbing service may then pass the reply onto the first service. When in a playback mode, the stubbing service may directly serve the stored reply to the first service in response to receiving the same request intended for the second service from the first service.

Stubbing techniques in distributed-services environments

Disclosed are various embodiments for generating a service call pattern for a system. A monitor is installed on a first and a second service call channel. Each service call channel is used by a first and second system under test, respectively. Through the monitor, service calls are received from the respective system under test. The service calls are issued to at least one service. A first service call pattern is generated based at least in part on the plurality of service calls issued by the first system under test. A second service call pattern is generated based at least in part on the plurality of service calls issued by the second under test. The first service call pattern report and the second service call pattern report are compared. An error condition if the comparison indicates a difference greater than a predefined threshold.

Generating service call patterns for systems under test

Unified and extensible meta-testing framework

Growing community of inventors

Seattle, WA, United States of America

Kyle Andrew Farrell